Alternatives and similar repositories for emergent-misalignment

Users that are interested in emergent-misalignment are comparing it to the libraries listed below

• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆193Updated 8 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆154Updated 2 months ago
• google-deepmind / mishax
  ☆134Updated 3 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆178Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆115Updated 4 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆243Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆193Updated this week
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆76Updated this week
• METR / task-standard
  METR Task Standard
  ☆154Updated 5 months ago
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆293Updated this week
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆210Updated last week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆99Updated this week
• METR / RE-Bench
  ☆92Updated 2 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆102Updated 3 weeks ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆220Updated 9 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆206Updated 7 months ago
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆109Updated last year
• METR / public-tasks
  ☆99Updated 4 months ago
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆224Updated this week
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago
• redwoodresearch / alignment_faking_public
  ☆69Updated last month
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆77Updated 7 months ago
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆88Updated 9 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆57Updated 8 months ago
• XuchanBao / behavioral-self-awareness
  ☆28Updated 4 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆173Updated 6 months ago
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆27Updated last month
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆52Updated this week
• anthropics / attribution-graphs-frontend
  https://transformer-circuits.pub/2025/attribution-graphs/methods.html
  ☆75Updated 3 months ago
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year